In federated learning, a central server coordinates the training of a single model on a massively distributed network of devices. This setting can be naturally extended to a multi-task learning framework, to handle real-world federated datasets that typically show strong statistical heterogeneity among devices. Despite…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,694 papers · 148 categories
Trend · papers per month
48 results for “server virtualization”
Paper introduces IAD for detecting anomalous VMMs in cloud without VMM access.
problem Anomalous VMMs in cloud-based environments without direct access.
method IAD: Indirect Anomalous VMMs Detection algorithm using VM resource utilization data.
result IAD algorithm outperforms other methods with an average F1-score of 83.7%.
Using Reinforcement Learning to Allocate and Manage Service Function Chains in Cellular Networkscs.NI
Paper uses RL to optimize SFC deployment and VNF management in NFV networks.
problem Optimizing SFC deployment and VNF management in NFV networks to reduce packet loss.
method Reinforcement Learning (PPO) to optimize SFC deployment and VNF management.
result PPO agent reduces packet loss in SFC deployment and VNF management.
Post-Quantum Secure Federated DeFi for Inclusive Banking
problem Financial systems and DeFi ecosystems are vulnerable to quantum computing threats.
method Post-Quantum Secure Federated DeFi framework using lattice-based FHE.
result End-to-end homomorphic computation enables inter-bank collaboration.
Privacy has raised considerable concerns recently, especially with the advent of information explosion and numerous data mining techniques to explore the information inside large volumes of data. In this context, a new distributed learning paradigm termed federated learning becomes prominent recently to tackle the priv…
The virtualization of compute and network resources enables an unseen flexibility for deploying network services. A wide spectrum of emerging technologies allows an ever-growing range of orchestration possibilities in cloud-based environments. But in this context it remains challenging to rhyme dynamic cloud configurat…
Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers. In this work, we describe methods to extend the federation framework to evaluate strategies for personalization of global models. We present tools to analyze the eff…
With the growing demand for data connectivity, network service providers are faced with the task of reducing their capital and operational expenses while simultaneously improving network performance and addressing the increased connectivity demand. Although Network Function Virtualization (NFV) has been identified as a…
Paper proposes CCVR to improve classifier calibration in federated learning with non-IID data.
problem Improving classifier calibration in federated learning with non-IID data.
method Proposes CCVR, a simple algorithm that adjusts the classifier using virtual representations.
result CCVR achieves state-of-the-art performance on popular federated learning benchmarks.
A new scheme for private computation splits client data into shares for server operations.
problem Private computation between client and server without revealing data.
method Stochastic scheme splitting client data into privatized shares.
result Server performs operations on privatized shares without learning raw data.
To keep up with increasing dataset sizes and model complexity, distributed training has become a necessity for large machine learning tasks. Parameter servers ease the implementation of distributed parameter management---a key concern in distributed training---, but can induce severe communication overhead. To reduce c…
Quantitative analysis of order-splitting behavior in Japanese stock market.
problem Understanding and quantifying the order-splitting behavior of traders in the Japanese stock market.
method Analysis of a large dataset of trading accounts over nine years, clustering traders into order-splitting and random traders, and applying statistical methods to analyze metaorder length and sign correlation.
result The metaorder length distribution follows power laws with exponent α, and the sign correlation exponent γ is approximately α-1, supporting the LMF model.
Distributed gradient descent (DGD) is an efficient way of implementing gradient descent (GD), especially for large data sets, by dividing the computation tasks into smaller subtasks and assigning to different computing servers (CSs) to be executed in parallel. In standard parallel execution, per-iteration waiting time …
Algorithm stabilizes queues in asymmetric systems with unknown service rates.
problem Stabilizing queues in multi-class multi-server systems with unknown service rates.
method Proposes UCB and Thompson Sampling algorithms to stabilize queues while learning service rates.
result Achieves system stability with an average queue length bound of \(O(\min\{N,K\}/ε)\) for large time horizon \(T\).
Corella protects client data privacy in multi-server learning with correlated queries.
problem Protecting client data privacy in multi-server machine learning.
method Proposes a private multi-server learning approach using correlated queries and strong noise.
result Mitigates client data leakage with high accuracy and minimal computational effort.
Federated learning has become increasingly important for modern machine learning, especially for data privacy-sensitive scenarios. Existing federated learning mostly adopts the central server-based architecture or centralized architecture. However, in many social network scenarios, centralized federated learning is not…
Machine Learning (ML) solutions are nowadays distributed and are prone to various types of component failures, which can be encompassed in so-called Byzantine behavior. This paper introduces LiuBei, a Byzantine-resilient ML algorithm that does not trust any individual component in the network (neither workers nor serve…
New method speeds up distributed linear regression.
problem Efficiently solve distributed linear regression problems.
method Iteratively Pre-conditioned Stochastic Gradient Descent (IPSG)
result Converges linearly in expectation to the solution.
Paper explores differential privacy in high-dimensional federated learning, tackling server trustworthiness and estimation.
problem Maintaining privacy in distributed environments with high-dimensional data.
method Investigates scenarios with untrusted and trusted central servers, introduces novel federated estimation algorithms for linear regression models.
result Tight minimax rates depend on high-dimensionality even with sparsity assumptions, and novel algorithms handle slight variations among distributed models.
To improve the quality of computation experience for mobile devices, mobile-edge computing (MEC) is a promising paradigm by providing computing capabilities in close proximity within a sliced radio access network (RAN), which supports both traditional communication and MEC services. Nevertheless, the design of computat…
This paper makes two contributions to Bayesian machine learning algorithms. Firstly, we propose stochastic natural gradient expectation propagation (SNEP), a novel alternative to expectation propagation (EP), a popular variational inference algorithm. SNEP is a black box variational algorithm, in that it does not requi…
Federated learning obtains a central model on the server by aggregating models trained locally on clients. As a result, federated learning does not require clients to upload their data to the server, thereby preserving the data privacy of the clients. One challenge in federated learning is to reduce the client-server c…
CSE-FSL reduces communication and storage costs in federated learning.
problem High communication and storage costs in federated learning.
method CSE-FSL uses an auxiliary network to locally update client models and sends only selected epochs' smashed data.
result Significant communication reduction with state-of-the-art convergence and model accuracy.
Machine Learning (ML) solutions are nowadays distributed, according to the so-called server/worker architecture. One server holds the model parameters while several workers train the model. Clearly, such architecture is prone to various types of component failures, which can be all encompassed within the spectrum of a …
New virtualized Δ-move simplifies virtual knots and links.
problem Simplifying virtual knots and links.
method Introducing a new local deformation called the virtualized Δ-move.
result Virtualized Δ-move is an unknotting operation for virtual knots.
Virtual index cocycles reformulate virtual link invariants.
problem No specific problem stated; focuses on reformulation.
method Using virtual index cocycles to reformulate invariants.
result Unified reformulation of virtual link invariants.
The paper studies strict equivalence in multi-virtual linkoids with new invariants.
problem Understanding strict equivalence in multi-virtual linkoids.
method Utilizing multi-virtual knot theory, defining strict virtual linkoids, and studying invariants.
result New invariants for strict virtual linkoids are defined.
New method reduces FL communication cost by leveraging server's side information.
problem High communication cost in federated learning.
method Exploits server's side information to compress client updates.
result Up to 82 times smaller bitrate with higher accuracy.
Communication on heterogeneous edge networks is a fundamental bottleneck in Federated Learning (FL), restricting both model capacity and user participation. To address this issue, we introduce two novel strategies to reduce communication costs: (1) the use of lossy compression on the global model sent server-to-client;…
Detects backdoors in outsourced models by replicating training steps across multiple servers.
problem Detecting backdoors in models trained on cloud providers without prior knowledge.
method Replicate training steps across multiple servers to identify deviations and malicious updates.
result 99.6% accuracy in identifying backdoored models out of 50% malicious providers.
Paper presents privacy-preserving techniques for HD computing.
problem Privacy loss in HD computing due to reversible computation.
method Quantization and pruning of hypervectors for differential privacy.
result Differentially private HD model for cloud inference.
This paper improves privacy in federated learning without a trusted server.
problem Privacy in federated learning with silos that distrust each other.
method Introduces Inter-Silo Record-Level Differential Privacy (ISRL-DP) and accelerated algorithms for convex and smooth losses.
result Achieves optimal privacy and accuracy tradeoffs in federated learning.
The study enumerates virtual quandles up to isomorphism.
problem Classifying virtual quandles up to isomorphism.
method Computer search and classification based on conjugacy class structures of rack automorphism groups.
result Classifications of virtual racks and quandles up to order 8.
Virtual Thompson's groupmath.GT
New virtual version of Thompson's group created to handle virtual knots.
problem Creating a mathematical framework for virtual knots.
method Defining a virtual version of Thompson's group and proving its properties.
result Any virtual link can be constructed from an element of the new virtual Thompson's group.
CF-moves for virtual linksmath.GT
The paper extends CF-moves to classify virtual links of any number of components.
problem Classifying virtual links using CF-moves.
method Extending CF-moves to classify virtual links of arbitrary number of components using the virtual linking number and invariants.
result Classification of 3-component even virtual links up to CF-moves.
Refines virtual link equality criterion for diagrams with one virtual crossing.
problem Determining when a virtual link diagram represents a properly virtual link.
method Refines the Kauffman-Murasugi-Thislethwaite type inequality for virtual links.
result Criterion for virtual link diagrams with exactly one virtual crossing to represent a properly virtual link.
Extend writhe polynomial from virtual knots to multi-virtual knots
problem Extend writhe polynomial from virtual knots to multi-virtual knots
method Extend writhe polynomial from virtual knots to multi-virtual knots
result Several questions asked in [16] have been answered
Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learningcs.LG
This work provides bounds on generalization error and privacy leakage in federated learning.
problem Bounding generalization error and privacy leakage in federated learning.
method Information-theoretic framework for classical, distributed, and federated learning.
result Upper and lower bounds on generalization error and privacy leakage.
New invariants for virtual knots and links defined via quiver representations.
problem Defining new invariants for virtual knots and links.
method Quiver representations associated to virtual biquandles and rings.
result New polynomial invariants for virtual knots and links.
Study virtualized Delta, Sharp, and Pass moves for oriented virtual knots and links.
problem Conditions for unknotting oriented virtual knots and links.
method Local moves (Delta, Sharp, Pass) for oriented virtual links.
result Lower bounds for the unknotting numbers are proven and shown to be best possible.
Paper tackles federated linear bandit learning with AirComp for noisy channels.
problem Minimize cumulative regret in federated linear bandit learning.
method Proposes a federated linear bandits scheme using over-the-air computation (AirComp) over noisy fading channels.
result Determines the regret bound of the proposed scheme.
The virtual unknotting number of a virtual knot is the minimal number of crossing changes that makes the virtual knot to be the unknot, which is defined only for virtual knots virtually homotopic to the unknot. We focus on the virtual knot obtained from the standard (p,q)-torus knot diagram by replacing all crossings o…
This paper connects virtual biquandles to biquandles for virtual link colorings.
problem Extending invariants from biquandles to virtual biquandles.
method Establishing equivalence between two representations of virtual braid groups and introducing new labeling rules.
result The number of colorings of a virtual link by virtual biquandles can be recovered from colorings by biquandles.
Virtual knots and links get multicrossings and petal diagrams.
problem Defining multicrossings for virtual knots and links.
method Extending multicrossings to virtual knots and links, showing petal diagrams exist.
result Petal diagrams exist for all virtual knots.
DFedAvgM is a decentralized FedAvg with momentum for privacy and communication efficiency.
problem Efficiently train models with privacy and communication efficiency in federated learning.
method Decentralized Federated Averaging with Momentum (DFedAvgM) on clients connected by an undirected graph, using stochastic gradient descent with momentum and quantization.
result DFedAvgM converges under trivial assumptions and can be improved with the PŁ property, numerically verified.
Paper proposes a GPU-based system for training massive deep learning models in ads systems.
problem Training massive deep learning models with terabyte-scale parameters in ads systems.
method Hierarchical GPU parameter server with 3-layer storage (GPU High-Bandwidth Memory, CPU main memory, SSD).
result 4-node hierarchical GPU parameter server trains a model 2X faster than a 150-node in-memory system.
A virtual string can be defined as an equivalence class of planar diagrams under certain kinds of diagrammatic moves. Virtual strings are related to virtual knots in that a simple operation on a virtual knot diagram produces a diagram for a virtual string. In this paper we consider three operations on a virtual string …
Paper improves communication in distributed optimization, reducing worker-to-server data exchanges.
problem Efficiency in server-to-worker communication in distributed optimization.
method MARINA-P, a novel downlink compression method using correlated compressors; M3, combining MARINA-P with uplink compression.
result MARINA-P achieves provably superior server-to-worker communication complexity with increasing number of workers.